{"id":"W2951052484","doi":"10.48550/arxiv.1405.0189","title":"On Hardness of Jumbled Indexing","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Omega; Search engine indexing; Combinatorics; Substring; Preprocessor; Matching (statistics); Mathematics; Sigma; Constant (computer programming); Pattern matching; Computer science; Algorithm; Data structure; Statistics; Information retrieval; Physics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002255683,0.0002284299,0.0003415328,0.0002261397,0.00009601995,0.00006370299,0.002142597,0.0002269565,0.00002381382],"category_scores_gemma":[0.00003261415,0.0002370604,0.0001481279,0.0002908376,0.00006068522,0.0002467077,0.00283436,0.0004281825,0.00005342424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000704374,"about_ca_system_score_gemma":0.0001123672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001056805,"about_ca_topic_score_gemma":0.000004211909,"domain_scores_codex":[0.9985189,0.0001114546,0.0001812757,0.0008403557,0.0001213035,0.0002266875],"domain_scores_gemma":[0.9977832,0.00009320552,0.000307362,0.001574959,0.0001282549,0.0001130022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005602013,0.000199722,0.0009106775,0.000184353,0.00008316746,0.0001460119,0.0001826983,0.2183051,0.00008910905,0.7730312,0.002566472,0.004245427],"study_design_scores_gemma":[0.0004726144,0.00007231967,0.0009707634,0.0003164668,0.00002382905,0.000001433387,0.00001025864,0.9155874,0.0004514561,0.08056244,0.001180461,0.0003506253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1216216,0.00001586242,0.8737809,0.00002461886,0.001063316,0.0001288654,0.0000136519,0.0001206247,0.003230513],"genre_scores_gemma":[0.996165,0.00002762929,0.00275566,0.00006414983,0.00005525278,3.679832e-7,0.00001545843,0.00001099938,0.0009054786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8745434,"threshold_uncertainty_score":0.9667044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0630169761731807,"score_gpt":0.1861705511471469,"score_spread":0.1231535749739662,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}